It looks like OpenCL is getting ready for prime time. A reader from across the English Channel contacted us with a link to Youtube video that showcases OpenCL being processed on a GPU. If I recall correctly, a while ago AMD claimed world’s first OpenCL demo, but it was done on a single core (and then scaled up to all four) on a Phenom II X4 CPU. If this video is correct, Nvidia gets the pole position for being the first company to demonstrate OpenCL working on a GPU, which is “usage as intended”. Judging from the video, Nvidia showed Nbody simulation changing following parameters:
Nvidia’s discloses its DP performance limitations
When Nvidia launched GT200 chip, the company claimed around 1TFLOPS of Single-Precision computing power, and roughly 150 GFLOPS of Dual-Precision performance. This discrepancy was mostly due to the fact that Nvidia went with dedicated hardware for the DP support. Every eight-shader cluster had one dedicated dual-precision unit, costing millions of additional transistors and resulted in doubtful performance. Fast forward to January 2009, and we have SP performance at 933 GFLOPS, while achievable DP performance dipped down to 78 GFLOPS. This figure is roughly half of what Nvidia boasted about at the time of launch, and sheer evidence that both manufacturers like to overstate the performance
University of Illinois streams its Parallel@Illinois seminars
Expanding on its role as CUDA Center of Excellence, University of Illinois in Urbana-Champaign is launching a 13-week seminar with focus on parallel computing. Well, GPU Computing, that is. Parallel@Illinois is the name for the whole project of GPU Computing, and this seminar was organized by prof. Sanjaj J. Patel and Wen-mei Hwu. Under a not-so-scientific moniker Need For Speed Seminar Series, this 13-week course will feature domestic alumni such as Mark Hasegawa-Johnson, Dan Roth, Narendra Ahuja, Stephen Boppart, John C. Hart, Tom Huang and Seth Hutchinson, and guests such as Keith Thulborn (UI Chicago), Sam Blackman (Elemental), Nikola Bozinovic (MotionDSP), Mark Johns (Tapulous) and
GPGPU is the future: Khronos releases OpenCL API
With Khronos group officially launching the OpenCL 1.0 specification, GPGPU computing is now officially covered with a open-source, royalty-free cross-platform API that enables parallel programming on the GPUs, regardless from whom they’re coming from.
ATI and Folding working on F@H 1.2.1: Performance, stability updates
Catalyst 8.12 drivers are set to debut next week, and as you probably know, this is no ordinary update. AMD GPG is bringing its STREAM middleware platform and updated libraries to every user of their GPGPU-enabled products (R520 “Fudo” chip aka Radeon 1800 and newer). As a part of AMD STREAM, ATI will release its own video transcoder for free. Given the limitations and performance that Badaboom has, I wonder did ATI decided to do something more in “formats supported” area. 😉 On the Folding@Home front, there are great expectations from this upcoming driver, especially if you own Radeon 4800 series product. ATI worked hard
Nvidia to bring SLI support for Folding@Home
Friends from Bjorn3D got the opportunity to interview Michael Steele, General Manager of Nvidia’s Visual Consumer Solutions group. Short explanation of Michael’s role would be Nvidia’s head for all-not-gaming-related things. The interview was focusing on Bjorn3D’s noteworthy Folding@Home effort (the team is on track to crack into Top100), thus Michael gave some interesting thoughts, such as this one. There are a lot of very good guides out there that will walk users through the required steps to fold with multiple GPUs like the ones on HardOCP or overclockers.co.uk, just not in SLI mode yet. NVIDIA SLI is a great extension to parallel processing and we’re
UPDATED: Nvidia set to launch Tesla powered Personal Supercomputer
Today is the first day of SuperComputing 08 conference held in Austin, Texas. A lot of companies are bringing out the big guns for that one, and one of the companies that could have the largest one is Nvidia and its partners. Regardless of what you may think of CUDA, this API really took off in scientific community. Young enthusiasts started to build personal supercomputers, and Nvidia CUDA guys got the idea of creating a personal supercomputer when they saw FASTRA project from University of Antwerp. FASTRA is being used for computational topography, but many other universities are doing exactly the same. Fast forward to
GPGPU Revolution: OpenCL to launch next week
If you’re wondering what is next week’s outlook for tech news, brace yourselves for impact. During the past three weeks, I was briefed by several companies and everybody is gearing up for SC08 (SuperComputing) conference in Austin, Texas. There will be a lot of announcements coming from AMD, Nvidia and Intel, but more importantly, Khronos group will show OpenCL (Open Computing Language) to the general audience. Many people view OpenCL as an API that will make the very same impact on consumer and professional applications that DirectX made in the world of games. If you’re in Austin, you can head over to Rio Grande Mexican
ASUS kills PATA and PCI standards!
Back on the INQ, I wrote about dangers lying ahead for AGEIA, Creative Labs and Bigfoot Networks, representatives of these respected companies just told me that their business model is solid and that they are indeed, future-proof. Well, that turned out nicely – AGEIA never took off because of $250 charge for a PCI card, Creative now exists almost solely on patent charges and selling off its own property, while Bigfoot networks made the greatest network card on the planet – and failed to pack it up in an attractive and future-proof package. The reason for this rant is a story on Xfastest.com, introducing ASUS
Nvidia’s $50 card destroys ATI’s $500 one or “Why ATI sucks in Folding?”
As you might already know, I am a bit enthusiastic when it comes to distributed computing. I’ve been looking for aliens through SETI@home, later with BOINC… but then, Folding@Home showed up and I became an enthusiast for this valuable project from Stanford University. My family had some share of dealings with Alzheimer’s (aka AD) and Parkinson’s diseases (aka PD) and I won’t go here into what psychological and ultimately financial stress that families around the world, including my own – have to endure. Folding@Home is also a project that pioneered the use of GPUs for distributed computing (if I am wrong on this one, feel
AMD releasing professional cards to partners – Sapphire first
Ever since AMD/ATI took over FireGL, the company was the only manufacturer of professional graphics cards. FireGL, FireStream, and now FirePro – they were all coming out with ATI logo on the box. But not anymore – AMD is going the Nvidia route and starting to introduce partners who will manufacture and sell the cards in a higher-standard program than is the case with consumer cards. As logic dictates, Sapphire Technologies was the first company to release a non-AMD manufactured professional card – FireStream 9250. We expect that more companies follow suit – I remember that Diamond introduced their FireGL cards in the Radeon 2900
Adobe ships GPU-accelerated Creative Studio 4, Flash Player 10
After reading countless previews and hearing the marketing buzz about some GPU-accelerated aspects of Photoshop, Premiere, After Effects and others, Adobe Systems announced immediate availability of whole CS4 package (Amazon.com still thinks these versions will be available in November). CS4 is divided into six new versions, as well as stand-alone versions. Adobe divided the packages to suit different content creators, thus package is divided into following: CS4 Design Premium CS4 Design Standard CS4 Design Web Premium CS4 Design Web Standard CS4 Design Production Premium CS4 Design Master Collection As you can imagine, these packages somewhat nothing else but “Premiere-in, Premiere-out” and so on. Professionals will
